conorbronsdon /avoid-ai-writing
Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.
★ 5,663⑂ 480👁 27⑃ 266● 160▤ 31
+26
日增长
5,663
stars
480
forks
27
watchers
266
prs
160
issues
31
releases
README
avoid-ai-writing
Audit & rewrite content to remove AI writing patterns. A practical skill for any AI agent. Supports detect-only and edit-in-place modes, plus voice profiles.
---
A portable writing skill for Claude Code, Codex, OpenClaw, Hermes, and any other agentskills.io-compatible agent. Audits and rewrites content to remove AI writing patterns ("AI-isms").
The rules and bundled detector are calibrated for English. See community language adaptations for independently maintained versions in other languages.
Three modes:
- Rewrite (default) — flags AI patterns, applies up to two editing passes, verifies the result when possible, and returns one final version.
- Detect — flags AI patterns without rewriting. Shows which flags are real problems vs. judgment calls. Useful when patterns might be intentional, when auditing content you don't want altered, or when you just want a quick scan.
- Edit — edits a prose file in place (via the Edit tool) with minimal, targeted changes, preserving passages that are already human. Source code, configuration, and generated data are refused because prose rewrites can corrupt structured content. Returns an edits-made + verification report, not the full file.
Use --iterate 1|2 to set the editing-pass ceiling. --iterate 1 allows the initial rewrite only. --iterate 2 uses the default maximum of an initial rewrite plus one correction or preservation repair, and stops early when no justified in-scope edit remains. Checks do not consume a pass, but any change they prompt does. The skill reports how many editing passes it used and any intentional, protected, or unresolved finding.
An optional voice profile (casual / professional / technical / warm / blunt) sets how the prose should sound, independent of the audience context profile.
The glossary defines the terms these docs use: word tiers, severity tiers, modes, profiles, and detector options.
Table of contents
- Quick demo
- Why a skill, not just a prompt
- Installation & Usage
Install the complete skill directory
Claude Code
Claude Cowork — install as a plugin
Google Antigravity
OpenClaw
Cursor
Hermes
OpenAI Codex
Native ChatGPT and Codex plugin package
Other agents
Triggering the skill
- Pattern reference
Content Patterns
Language Patterns
Structure Patterns
Communication Patterns
Meta Patterns
Structural Detection (v3.4)
AI-tool fingerprints & later additions (v3.5–3.8)
Conversational-register patterns (v3.15)
Share-post framing (v3.20)
Narrated candor (v3.21)
Unnecessary hyphenation (v3.24)
- Full Example
- Run the detector
Score a file or piped text from the command line
Gate prose in GitHub Actions or pre-commit
Use the detector over MCP
- Pre-publish pipeline
- House style is a different job
- More from me
- Credits
- Community / Multilingual
- Official sources and sponsorship
- Disclaimer
- License
Quick demo
InpuTop issues
#249Audit uncited "AI writes X / humans write Y" claims in the catalog5 comments · 2026-09-12#122Evaluate destination-aware hard-wrap detection; skill guidance shipped3 comments · 2026-08-07#94Publish the detector as a Vale package: the registry has 16 style packages and none targets AI-writing tells2 comments · 2026-08-03#125Variants per model family?1 comments · 2026-08-10#85Expand human-corpus coverage: docs, conversational, social and email1 comments · 2026-08-02#351Resolve remaining site-audit false positives and rendered-input questions0 comments · 2026-09-27#322Resolve final rewrite scope and reporting regressions0 comments · 2026-09-16#206Follow up the editorial-card pilot with full-catalog coverage checks0 comments · 2026-09-12
Latest release
v3.38.0 v3.38.0 2026-10-15Changed - Replaced placeholder instructions and empty suggestions in the word replacement tables with concrete, direct alternatives for previously incomplete entries (215). - Removed breakthrough from the game-changer / game-changing suggestions to avoid preserving unsupported importance claims. Added missing context fallbacks and adjective/noun clarifications for transformative, paradigm-shifting, and despite challenges (380). - Ground model-only detect audit findings in the pattern catalog: report only catalog patterns with canonical categories and severities (e.g., transition phrases and g